Semantically search the codebase for relevant code fragments. Returns the most similar code chunks with file paths and line numbers. Use this when you need to find WHERE something is implemented.
AI agents call search_context to retrieve information from Contextflow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs code search and retrieval operations only. It reads and queries the vectorized repository to locate code fragments matching semantic criteria, then returns results. There are no side effects, no data modification, no code execution, and no destructive operations. The tool is purely informational and non-intrusive, making it a Read category risk with low severity.
From the tool's definition Tool description states it "semantically search[es] the codebase for relevant code fragments" and "Returns the most similar code chunks with file paths and line numbers." The verb "search" and "returns" indicate data retrieval with no modification, creation,…
Attacks that exploit this kind of access
Semantically search the codebase for relevant code fragments. Returns the most similar code chunks with file paths and line numbers. Use this when you need to find WHERE something is implemented. It is categorised as a Read tool in the Contextflow MCP Server, which means it retrieves data without modifying state.
Register the Contextflow MCP server in PolicyLayer and add a rule for search_context: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Contextflow. Nothing to install.
search_context is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the search_context rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for search_context. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
search_context is provided by the Contextflow MCP server (millermarru/mcpcontext). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →